Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    listing capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    I
    0.37
    another
    0.33
    ିକ
    0.33
     המ
    0.33
     района
    0.32
    any
    0.31
    ባድ
    0.31
     luar
    0.31
     legnagyobb
    0.30
    which
    0.30
    POSITIVE LOGITS
     indeed
    0.66
     actually
    0.53
     invariably
    0.49
     infatti
    0.49
     certainly
    0.49
     typically
    0.48
     theoretically
    0.47
     undoubtedly
    0.46
     routinely
    0.46
     often
    0.46
    Act Density 0.650%

    No Known Activations